CN111026909B - Method for supplementing public security investigation data set based on self-timer tremble sound view - Google Patents
Method for supplementing public security investigation data set based on self-timer tremble sound view Download PDFInfo
- Publication number
- CN111026909B CN111026909B CN201911208381.1A CN201911208381A CN111026909B CN 111026909 B CN111026909 B CN 111026909B CN 201911208381 A CN201911208381 A CN 201911208381A CN 111026909 B CN111026909 B CN 111026909B
- Authority
- CN
- China
- Prior art keywords
- short video
- information
- public security
- face
- analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/71—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7837—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content
- G06F16/784—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content the detected or recognised objects being people
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/787—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a method for supplementing public security investigation data sets based on a self-timer tremble sound view. The method comprises the steps of utilizing a customized interface to dock a short video content service platform, obtaining a network short video, receiving, storing and establishing a network short video library according to a view library standard, utilizing an AI analysis system to extract target information according to the view library standard to form a short video view database, utilizing a face, a human body and other target images subjected to face beautification to be supplemented to the short video view database, utilizing secondary AI analysis to extract target information from the face, the human body and other target images subjected to face beautification to be supplemented to the short video view database, and utilizing fusion multidimensional analysis of public security big data. The method realizes the data mining of the short video view data.
Description
Technical Field
The invention belongs to the technical field of monitoring, and relates to a method for supplementing public security detection data sets based on self-timer tremble sound views.
Background
The public security investigation department collects various data to form public security big data, the public security big data are collected to a public security big data platform, public security department in 2019 issues public security big data series standards such as GA/DSJ200-2019 public security big data processing general technical Specification, and public security collection, processing and public security big data application are standardized.
The spatiotemporal characteristics in public security big data play an important role in spatiotemporal trajectory analysis. The space-time characteristic refers to an information record with time and space position, for example, a vehicle gate record comprises related information such as time, place (longitude and latitude), direction, speed, lane, site photo and the like of a vehicle passing through an electronic gate; for example, the video face card slot also records the information such as the time point, the place (longitude and latitude) and the face/human identification information when the pedestrian passes through the face card slot.
The space-time analysis of public security big data mainly refers to analysis based on space-time track class:
(1) And (3) track inscription: for example, the track of a person or a car is characterized, and all records of the person or the car in a certain period/range are scattered on a map to form a visual track based on GIS.
(2) Identity portraits: by analyzing the track of the person and the car, the activity attribute of the person and the car can be analyzed in which time periods and which places are frequently passed, such as an express delivery person (the activity is in a district), a cleaner (the work is earlier and in a certain route), a office worker (the person often enters and exits in a certain address such as home and unit in a fixed time period), and the like.
(3) Accompanying analysis: by analyzing the tracks of people and vehicles, the possible peers and vehicles can be extracted from the people and vehicles passing at the same/similar time sequence and places, and whether to work as peers or not is analyzed
(4) Special trajectories: by analyzing the human and vehicle trajectories of a certain period/area range, whether all enter the district or not, and do not leave (only enter and not exit or only exit and not enter), or only enter and exit once, or deliberately bypass and other special behavior trajectories.
However, due to the limitation of information collected by public security departments, all track records (image records and electromagnetic records) of possible criminal suspects cannot be completely collected, and the situation of lack of case key clues is often caused in public security investigation activities. Especially, the video investigation currently being public security video monitoring system is used as the main investigation means, and due to the limitation of the distribution points of the monitoring cameras, all scenes cannot be covered (currently, only about 3000 ten thousand public security monitors are carried out in 960 ten thousand square kilometers), the video investigation has a certain collision gas component, and if more people and vehicles can be acquired, the video investigation can be more helpful.
Short video is entertainment type music video with special fire in recent years, under the strong promotion of fast hands, tremble voice and the like, only the tremble voice platform has 3.2 hundred million active users nationwide at present, the number of logging in per person is 13.5 days/month, and millions of short video numbers are released on line every day. Such a plurality of shortcuts contain a large amount of information about people and vehicles. And the short videos can be acquired through GPS positioning service to obtain the position information (longitude and latitude) when shooting, namely the short videos have space-time information, most (more than 90 percent) of the short videos are based on people from the current trembling, and if the short videos are used as important information sources of multi-dimensional information in public security video investigation work, more line-of-sight information sources can be provided.
The following technical content is disclosed in basic theoretical research of public security information data mining technology published in the period 233 of safety & Automation. Every person must leave a track of activity such as hotel, internet surfing, shopping, employment, etc.; for example, a track of a route can be formed by sitting on a car and walking; if the mobile phone is carried with the user, the mobile phone mobile switching cellular base station can leave the track of the mobile phone. Thus, a "three-way/multiple-way trajectory collision" theory can be summarized: the track formed by the actions of a person such as temporary holding, accommodation, surfing, employment, traveling, and the like is a 'person track', the track of a holding vehicle (road monitoring, photographing, vehicle management record, maintenance record, and the like) is a 'vehicle track', the track of a holding mobile phone (network track, WIFI-MAC track, cellular or GPS positioning, and the like) is a 'mobile phone track', and the track corresponding to the virtual identity (social account number, game account number, and the like) is a virtual track. Various action tracks can be visually displayed on a map through collection, cleaning and processing, and information such as occupation, daily life tracks and the like of the person can be judged. If multiple trails of criminals are available, multidimensional track collision simulation analysis can be performed. The case-related track in case investigation is combined with the high co-orbit track which is obtained by data mining and is matched with the case track in time and space, and the obtained recommended suspects are ranked, so that multipoint track collision analysis can be carried out, screening and suspects are carried out, and suspects are finally determined. The technology is put into use in a space-time analysis platform of the public security bureau of the Zhejiang province, but is limited to space-time track analysis and judgment among motor vehicle bayonets, WIFI acquisition data, RFID electric vehicle passing data, case library data of management cases and the like, and does not have the scheme of fusion and judgment on face track data extracted based on face intelligent analysis and application of face and vehicle information data based on short video platforms such as tremble sounds and the like.
One existing technology at present is view query and retrieval and data association analysis based on public security video image intelligent application technology.
The query and search service provides semantic query and search based on characteristic attributes, such as original video, pictures, structured data, basic data of sensing equipment and the like, and supports accurate query, fuzzy query and combined condition query.
(1) Video retrieval: the text semantic description search for the video clips is supported to be input, and the text semantic description search can be a keyword or a description word, and information such as video related to similar scenes, hit positions, scene descriptions and the like is returned.
(2) And (5) searching pictures: text semantic description retrieval for pictures is supported, which can be keywords or a descriptive text, and the pictures related to similar scenes and corresponding descriptions are returned.
(3) And (5) file retrieval: the text semantic description search for the file is supported to be input, and the text semantic description search can be a keyword or a descriptive text, and a similar file path is returned.
(4) And (5) structured data retrieval: the method is used for inquiring the structured data and supporting accurate matching and fuzzy matching.
(5) Full text retrieval: the text is supported to be used as a query condition for searching, and the input keywords can be automatically and intelligently matched.
(6) Cascading queries and searches: support to forward the query instruction to the subordinate or flat video image data service according to the query condition, support to forward the query result to query operation initiator; and the query command is distributed to the subordinate or level video image data service according to the query condition, and the search results returned by the local and all subordinate or level services are summarized and combined and forwarded to the query operation initiator.
And (3) data association: the method is characterized in that the video image structural data is associated with other business data according to association rules, and feature attribute association, space-time track association, video image association and the like of people/vehicles/objects are supported.
(1) Feature attribute association: in general, the data of incomplete personnel, vehicles, articles and the like after the analysis processing of video images are associated with characteristic attributes (including identities, relations, behaviors and the like) identified from other business data, and the associated characteristic attribute information is backfilled into personnel/vehicles/article archives, so that the value of the data of personnel, vehicles, articles and the like is improved.
(2) Space-time trajectory correlation: and (3) correlating the video image structuring, wiFi/RFID, public security service data and other space track related data with personnel, vehicles and articles, enriching space-time data of the personnel, vehicles, articles and other objects, and supporting multi-track fusion correlation.
(3) Video image association: and associating the video clips and the snap shots with objects such as specific personnel, vehicles and articles.
The technical scheme of view query and retrieval and data association analysis of the intelligent application technology of the public security video image is based on multidimensional data fusion application and research analysis under the existing public security video big data. But the view data of public security come from the view intelligent analysis of public security video monitoring system/snowing engineering, and the collection, processing and application of a large amount of short videos from a network platform are not involved.
Disclosure of Invention
Big data inquiry during public security investigation is based on bayonet to perform space-time track collision, but coverage is limited after all. And the common people like playing the self-timer and shaking the voice, and the terminal is required to synchronously upload GPS positioning data (both supported by the mobile phone) when uploading pictures and videos. The short video is obtained by cooperation with content service providers such as tremble voice and fast handoffs and serves as an important source of public security video investigation data, information such as key characteristic attributes and the like is extracted from the network short video through an intelligent analysis technology and is brought into a data source of the public security large data, network video data are fused through public security investigation business, and diversity of public security investigation data sources is achieved. The invention aims to provide a method for supplementing public security investigation data sets based on self-timer tremble sound views.
The method comprises the following steps:
(1) Utilizing a customized interface to dock the short video content service platform to obtain a network short video;
(2) Receiving, storing and establishing a network short video library according to the view library standard;
(3) Extracting target information by using an AI analysis system according to a view library standard to form a short video view database;
(4) Restoring the target images of the face, the human body and the like subjected to face beautification by using the face-beautifying technology, and supplementing the target images to a short video view database;
(5) Extracting target information from target images such as face and human body subjected to face beautifying restoration by utilizing secondary AI analysis, and supplementing the target information to a short video view database;
(6) And realizing data mining of the short video view data by utilizing fusion multidimensional analysis of public security big data.
When public security makes space-time inquiry, vehicle models with large suspicion, human faces and human bodies of license plates are filtered, then multi-dimensional data sets are acquired from several important content service providers in a targeted mode to search the pictures, video investigation clues are acquired to increase the case breaking rate, and meanwhile invalid data quantity is reduced as much as possible.
The method specifically comprises the following steps:
(1) Collecting short video images of a content service provider: the public security organization collects short video images and related information from the content service provider platform in real time/at fixed time in a customized interface mode, wherein the related information comprises shooting time, place and photographer, and forms a sub-library of a public security video library, namely a network short video library;
(2) Extracting the information of people and vehicles of the short video image: extracting target information, characteristic attribute information and characteristic vectors comprising personnel/human bodies and vehicles from the short video image by using a video image AI analysis algorithm to form a short video view database;
(3) Face/body confrontation and beauty secondary analysis: the AI analysis algorithm of the face and the human body is used for extracting the pictures of the face and the human body from the short video view database by using the video image to perform secondary analysis, the face and the human body images processed by the face and the human body are restored, and the restored video image is analyzed and extracted to obtain information and is supplemented to the short video view database;
(4) Public security investigation of suspected targets/trajectories: the police extracts the information of the suspected target, the suspected feature and the suspected person/vehicle track;
(5) Deep analysis of tremble image content: if the head portraits of the suspects only appear in the background, recording the head portraits of the suspects as the time-space points of the general suspects; if the suspects and the tremble photographers are close to each other and appear in the foreground, the related information of the photographers is taken as the information points of the suspects;
(6) Short video view database retrieval: extracting the information of the detected suspected targets, suspected features and suspected person/vehicle tracks into a short video view database for retrieval as later application;
(7) Checking the detailed information: and inquiring suspicion information mined from the short video view database through an interface authorized by the content service provider platform, and calling detailed information of the publisher so as to assist public security investigation.
The method comprises the steps of utilizing a customized interface to dock a short video content service platform, obtaining a network short video, receiving, storing and establishing a network short video library according to a view library standard, utilizing an AI analysis system to extract target information according to the view library standard to form a short video view database, utilizing a face, a human body and other target images subjected to face beautification to be restored by a face-beautifying technology to supplement the short video view database, utilizing a secondary AI analysis to extract target information from the face, the human body and other target images subjected to face beautification to supplement the short video view database, and utilizing fusion multidimensional analysis of public security big data to realize data mining of the short video view data.
Detailed Description
A method for supplementing public security investigation data sets based on self-timer tremble sound views specifically comprises the following steps:
(1) Collecting short video images of a content service provider: the public security organization collects short video images and related information from a content service provider platform in real time (collected after terminal release online review)/at regular time (updated every day at leisure) in a customized interface mode according to national regulations, cooperation win-win and safety management and control as the premise, wherein the related information comprises shooting time, place and photographers, and a sub-library of a public security video library, namely a network short video library, is formed.
The network short video library is based on short videos of content service providers and related information, if the network short video library relates to business secrets and privacy of network video release users, desensitization processing (removing detailed client key information and only associating with ID numbers) can be adopted, and when detailed information is needed, related detailed information of a content service provider platform is queried through a high-authorization client.
(2) Extracting the information of people and vehicles of the short video image: the method comprises the steps of extracting target information, characteristic attribute information and characteristic vectors (a group of data describing images of people/human bodies and vehicles) comprising people/human bodies and vehicles from short video images according to interfaces and view library standards of GA/T1399-2017 public security video image analysis systems and GA/T1400-2017 public security video image information application systems by using a video image AI analysis algorithm to form a short video view database.
In order to improve the usability of video images, information extraction of video images is required. From which structured information (time, place, person/car feature attribute information), semi-structured information (person/car feature vectors), unstructured information (person/car panoramas, partial close-up small figures, etc.), view information extraction requires the use of artificial intelligence algorithms and analytical computing resources.
(3) Face/body confrontation and beauty secondary analysis: the method comprises the steps of extracting face and human body pictures from a short video view database according to an interface and view library standard of GA/T1400-2017 public security video image information application system by using an AI analysis algorithm of video image face-beautifying, carrying out secondary analysis, restoring face and human body images subjected to face-beautifying treatment, analyzing and extracting information of the restored video image, and supplementing the information to the short video view database.
The short video released in the network is mostly subjected to face beautifying treatment, the face and the human body are artificially changed, the changed view is distorted, the automatic comparison cannot be performed as the automatic comparison of intelligent video investigation, and the face beautifying restoration is required. At present, various restoration algorithms for beautifying can be adopted in the industry. The pictures subjected to the beauty restoration are required to be stored with the same information of the original view library or stored in association with the same ID so as to be convenient for subsequent comparison, inquiry and rechecking; the restored picture needs to be analyzed again to extract view information, and the view information is stored in a short video view database before restoration.
(4) Public security investigation of suspected targets/trajectories: public security performs comprehensive research and judgment analysis through various detection means such as field investigation, technical detection, view detection, network technology and the like and public security big data, and extracts information of suspected targets, suspected features and suspected person/vehicle tracks.
The public security detection means are various, and four detection integration fusion detection means of technical detection, websites, criminal detection and map detection are mostly adopted at present. The primary goal of public security is case breaking, and the primary work of case breaking is to extract suspected targets and capture and return cases. Because suspicion information acquired by various investigation means is intermittent, comprehensive research and judgment are required, and a combined combat mode of a cooperative combat center is generally adopted.
(5) Deep analysis of tremble image content: if the head portraits of the suspects only appear in the background, recording the head portraits of the suspects as the time-space points of the general suspects; if the suspects and the tremble photographers are close to each other and appear in the foreground, the related information (such as social attributes of communities, activities and the like) of the photographers is taken as the information points of the suspects.
For example, in the case of attribute track collision, if the video trace is broken, the only information is that the suspects may appear at some time and some place, and then the empty track collision is detected by detecting information and the like with the mobile phone signal and Mac. If a suspected person's close partner exists in a certain video image, the trajectory information of the suspected person can be indirectly found by searching the trajectory, view data, space-time collision and the like of the close partner.
In public security investigation, the head portraits of the suspects possibly appear in the background images of the short videos, but when the faces are not clear, the head portraits are marked to be used as a space-time record (space: in the scene of a certain camera; time; at a certain time point) of the suspects, and the head portraits are used as one of track points in the future of space-time collision. If the images of the suspected person in the images have the relatives and partners, the related information of the photographer is taken as the information of the suspected person together, and the information can be used for full-text searching (text labeling) and picture searching (face picture) later.
(6) Short video view database retrieval: and extracting the information of the detected suspected targets, the suspected features and the suspected person/vehicle tracks into a short video view database for searching, studying and judging and analyzing, so as to realize the applications of suspected target clue searching, map searching, track searching, map distributing and the like.
After the public security obtains suspicion information through various investigation means, the suspicion information can be continuously detected in the short video view database, the short video view database and public security big data can be fused to carry out multidimensional data retrieval and research analysis, suspicion control of network videos can be carried out, and when suspicion targets exist in views issued by a user terminal, an alarm can be triggered.
(7) Checking the detailed information: and inquiring suspicion information mined from the short video view database through an interface authorized by the content service provider platform, and calling detailed information of the publisher so as to assist public security investigation.
When detailed information cannot be provided due to reasons such as content service provider platform operation and user privacy protection, the content service provider can be required to assist in investigation and discovery of suspected information, and more detailed information can be provided.
Claims (1)
1. A method for supplementing public security investigation data sets based on self-timer tremble sound views is characterized by comprising the following steps:
(1) Collecting short video images of a content service provider: the public security organization collects short video images and related information from the content service provider platform in real time/at fixed time in a customized interface mode, wherein the related information comprises shooting time, place and photographer, and forms a sub-library of a public security video library, namely a network short video library;
(2) Extracting the information of people and vehicles of the short video image: extracting target information, characteristic attribute information and characteristic vectors comprising personnel/human bodies and vehicles from the short video image by using a video image AI analysis algorithm to form a short video view database;
(3) Face/body confrontation and beauty secondary analysis: the AI analysis algorithm of the face and the human body is used for extracting the pictures of the face and the human body from the short video view database by using the video image to perform secondary analysis, the face and the human body images processed by the face and the human body are restored, and the restored video image is analyzed and extracted to obtain information and is supplemented to the short video view database;
(4) Public security investigation of suspected targets/trajectories: the police extracts the information of the suspected target, the suspected feature and the suspected person/vehicle track;
(5) Deep analysis of tremble image content: if the head portraits of the suspects only appear in the background, recording the head portraits of the suspects as the time-space points of the general suspects; if the suspects and the tremble photographers are close to each other and appear in the foreground, the related information of the photographers is taken as the information points of the suspects;
(6) Short video view database retrieval: extracting the information of the detected suspected targets, suspected features and suspected person/vehicle tracks into a short video view database for retrieval as later application;
(7) Checking the detailed information: and inquiring suspicion information mined from the short video view database through an interface authorized by the content service provider platform, and calling detailed information of the publisher so as to assist public security investigation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911208381.1A CN111026909B (en) | 2019-11-30 | 2019-11-30 | Method for supplementing public security investigation data set based on self-timer tremble sound view |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911208381.1A CN111026909B (en) | 2019-11-30 | 2019-11-30 | Method for supplementing public security investigation data set based on self-timer tremble sound view |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111026909A CN111026909A (en) | 2020-04-17 |
| CN111026909B true CN111026909B (en) | 2023-04-28 |
Family
ID=70207303
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911208381.1A Active CN111026909B (en) | 2019-11-30 | 2019-11-30 | Method for supplementing public security investigation data set based on self-timer tremble sound view |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111026909B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112214638B (en) * | 2020-10-20 | 2023-04-21 | 湖南快乐阳光互动娱乐传媒有限公司 | Video content deconstructing method and system based on big data mining |
| CN113239041A (en) * | 2021-05-13 | 2021-08-10 | 大连交通大学 | Computer big data processing acquisition system and method |
| CN114265952B (en) * | 2022-03-02 | 2023-03-14 | 浙江宇视科技有限公司 | Target retrieval method and device |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101266704A (en) * | 2008-04-24 | 2008-09-17 | 张宏志 | ATM secure authentication and pre-alarming method based on face recognition |
| CN103237201A (en) * | 2013-04-28 | 2013-08-07 | 江苏物联网研究发展中心 | Case video studying and judging method based on social annotation |
| WO2016180224A1 (en) * | 2015-05-11 | 2016-11-17 | 北京锤子数码科技有限公司 | Method and device for processing image of person |
| CN106534798A (en) * | 2016-12-06 | 2017-03-22 | 武汉烽火众智数字技术有限责任公司 | Integrated multidimensional data application system for security monitoring and method thereof |
| CN106657867A (en) * | 2015-08-12 | 2017-05-10 | 杭州海康威视数字技术股份有限公司 | Mobile terminal alarming method and apparatus based on video monitoring system |
| CN106713700A (en) * | 2016-12-08 | 2017-05-24 | 宇龙计算机通信科技(深圳)有限公司 | Picture processing method and apparatus, as well as terminal |
| CN107301389A (en) * | 2017-06-16 | 2017-10-27 | 广东欧珀移动通信有限公司 | Based on face characteristic identification user's property method for distinguishing, device and terminal |
| CN107967348A (en) * | 2017-12-13 | 2018-04-27 | 武汉烽火众智数字技术有限责任公司 | The system and method for video investigation efficiency are improved based on more network data fusion applications |
| CN109492604A (en) * | 2018-11-23 | 2019-03-19 | 北京嘉华科盈信息系统有限公司 | Faceform's characteristic statistics analysis system |
| CN110188238A (en) * | 2019-05-15 | 2019-08-30 | 上海良相智能化工程有限公司 | A kind of wisdom public security video frequency search system |
| CN110213651A (en) * | 2019-05-28 | 2019-09-06 | 暨南大学 | A kind of intelligent merit Computer Aided Analysis System and method based on security protection video |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9754355B2 (en) * | 2015-01-09 | 2017-09-05 | Snap Inc. | Object recognition based photo filters |
-
2019
- 2019-11-30 CN CN201911208381.1A patent/CN111026909B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101266704A (en) * | 2008-04-24 | 2008-09-17 | 张宏志 | ATM secure authentication and pre-alarming method based on face recognition |
| CN103237201A (en) * | 2013-04-28 | 2013-08-07 | 江苏物联网研究发展中心 | Case video studying and judging method based on social annotation |
| WO2016180224A1 (en) * | 2015-05-11 | 2016-11-17 | 北京锤子数码科技有限公司 | Method and device for processing image of person |
| CN106657867A (en) * | 2015-08-12 | 2017-05-10 | 杭州海康威视数字技术股份有限公司 | Mobile terminal alarming method and apparatus based on video monitoring system |
| CN106534798A (en) * | 2016-12-06 | 2017-03-22 | 武汉烽火众智数字技术有限责任公司 | Integrated multidimensional data application system for security monitoring and method thereof |
| CN106713700A (en) * | 2016-12-08 | 2017-05-24 | 宇龙计算机通信科技(深圳)有限公司 | Picture processing method and apparatus, as well as terminal |
| CN107301389A (en) * | 2017-06-16 | 2017-10-27 | 广东欧珀移动通信有限公司 | Based on face characteristic identification user's property method for distinguishing, device and terminal |
| CN107967348A (en) * | 2017-12-13 | 2018-04-27 | 武汉烽火众智数字技术有限责任公司 | The system and method for video investigation efficiency are improved based on more network data fusion applications |
| CN109492604A (en) * | 2018-11-23 | 2019-03-19 | 北京嘉华科盈信息系统有限公司 | Faceform's characteristic statistics analysis system |
| CN110188238A (en) * | 2019-05-15 | 2019-08-30 | 上海良相智能化工程有限公司 | A kind of wisdom public security video frequency search system |
| CN110213651A (en) * | 2019-05-28 | 2019-09-06 | 暨南大学 | A kind of intelligent merit Computer Aided Analysis System and method based on security protection video |
Non-Patent Citations (3)
| Title |
|---|
| 唐文杰.公安警务领域视频图像侦查关键技术综述.《中国公共安全》.2017,第301卷(第301期),108-112. * |
| 梅蓉 等.图像处理技术在视频监控图像侦查中的应用.《广东公安科技》.2013,第21卷(第21期),49-51. * |
| 郑秋文 等.结合深度Q学习和注意模型的视频人脸识别.《信息技术》.2019,第43卷(第43期),111-115+120. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111026909A (en) | 2020-04-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111026909B (en) | Method for supplementing public security investigation data set based on self-timer tremble sound view | |
| US10974829B2 (en) | Drone device security system for protecting a package | |
| Shao et al. | Smart monitoring cameras driven intelligent processing to big surveillance video data | |
| KR20140095956A (en) | Method and system for generating image-knowledge contents based on crowdsourcing | |
| US20080273088A1 (en) | Intelligent surveillance system and method for integrated event based surveillance | |
| US20150070506A1 (en) | Event triggered location based participatory surveillance | |
| US20120207356A1 (en) | Targeted content acquisition using image analysis | |
| CN104978571A (en) | Intelligent dynamic high-definition video detection system | |
| CN113378616A (en) | Video analysis method, video analysis management method and related equipment | |
| CN109784220B (en) | Method and device for determining passerby track | |
| CN107172065B (en) | Intelligent sharing method and system for on-site video | |
| CN111209784A (en) | Police system based on intelligent wearable device | |
| CN112383751A (en) | Monitoring video data processing method and device, terminal equipment and storage medium | |
| CN112365520A (en) | Pedestrian target real-time tracking system and method based on video big data resource efficiency evaluation | |
| CN112711964A (en) | Face tracking monitoring system and method | |
| CN210983509U (en) | Entry key group distribution and control system | |
| CN114677627A (en) | Target clue finding method, device, equipment and medium | |
| van Rooijen et al. | Rapid person re-identification retraining strategy for flexible deployment in new environments | |
| Harris | The Panopticon v. the Capitol Rioters: Forensic technology is enormously powerful, but is it worth the privacy trade-offs? | |
| WO2015188231A1 (en) | Enforcement services techniques | |
| JP2021099709A (en) | Investigation support system and investigation support method | |
| Dai et al. | A study on Singapore haze | |
| Podzolkova et al. | Use of Information Systems in Disclosure of Criminal Offenses | |
| Kumar et al. | Intelligent Surveillance System Using Sum of Absolute Difference Algorithm | |
| DAI et al. | A study on Singapore haze.(2016) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |